A method for real-time fusion of multi-sensor information of unmanned vehicle
The invention discloses a method for real-time fusion of multi-sensor information of an unmanned vehicle, which comprises the following steps: determining a priori probability of each sensor; Determining an initial mass function; Calculating the correlation degree; According to the correlation degre...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
26.03.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a method for real-time fusion of multi-sensor information of an unmanned vehicle, which comprises the following steps: determining a priori probability of each sensor; Determining an initial mass function; Calculating the correlation degree; According to the correlation degree, the trust set, fuzzy set and risk set are obtained. Computing the risk function of trust set, fuzzy set and risk set; Calculating a posterior probability; Comparing the posterior probability of each sensor with a preset risk threshold; correcting The initial mass function of each sensor corresponding to each target information according to the following equation; Conducting D-S multiplication fusion, acquiring the fusion probability of each target information after the unmanned vehicle sensorsystem is recognized. A priori factor for measuring uncertainty is introduced to carry out risk assessment by using data association distribution, and the quantization treatment of uncertainty can effectively avoid the influ |
---|---|
Bibliography: | Application Number: CN201811230225 |